Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    information about performance metrics and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vik
    -0.15
    bedo
    -0.15
    eniable
    -0.14
    apis
    -0.14
    ienne
    -0.14
    ModelProperty
    -0.14
    pane
    -0.13
     Alo
    -0.13
    æµľ
    -0.13
    phan
    -0.13
    POSITIVE LOGITS
    ãĥ³ãĥĸ
    0.17
    enin
    0.15
    thouse
    0.15
     enough
    0.15
    undle
    0.15
     arbitrary
    0.15
     sufficient
    0.14
    αÏģ
    0.14
     plenty
    0.14
     suf
    0.14
    Act Density 0.105%

    No Known Activations